Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 333 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.1989. Min Act: -0.1700

Data Index: 224327 (C4 (Web Text))

Max Activating Token Index: 600

Text #1

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.2302. Min Act: -0.1700

Data Index: 1251414 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.2614. Min Act: -0.1700

Data Index: 170960 (C4 (Web Text))

Max Activating Token Index: 262

Text #3

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.1677. Min Act: -0.1700

Data Index: 45601 (C4 (Web Text))

Max Activating Token Index: 743

Text #4

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.1364. Min Act: -0.1700

Data Index: 776608 (C4 (Web Text))

Max Activating Token Index: 62

Text #5

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.1364. Min Act: -0.1700

Data Index: 1356338 (C4 (Web Text))

Max Activating Token Index: 313

Text #6

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.1364. Min Act: -0.1700

Data Index: 603478 (C4 (Web Text))

Max Activating Token Index: 314

Text #7

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.1364. Min Act: -0.1700

Data Index: 396926 (C4 (Web Text))

Max Activating Token Index: 140

Text #8

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.1052. Min Act: -0.1700

Data Index: 345994 (C4 (Web Text))

Max Activating Token Index: 812

Text #9

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.1052. Min Act: -0.1699

Data Index: 1158955 (C4 (Web Text))

Max Activating Token Index: 172

Text #10

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.0427. Min Act: -0.1700

Data Index: 1255878 (C4 (Web Text))

Max Activating Token Index: 392

Text #11

Max Range: 5.2614. Min Range: -5.2614

Max Act: 5.0114. Min Act: -0.1700

Data Index: 279786 (C4 (Web Text))

Max Activating Token Index: 211

Text #12

Max Range: 5.2614. Min Range: -5.2614

Max Act: 4.9802. Min Act: -0.1700

Data Index: 570722 (C4 (Web Text))

Max Activating Token Index: 284

Text #13

Max Range: 5.2614. Min Range: -5.2614

Max Act: 4.9802. Min Act: -0.1700

Data Index: 762194 (C4 (Web Text))

Max Activating Token Index: 594

Text #14

Max Range: 5.2614. Min Range: -5.2614

Max Act: 4.9177. Min Act: -0.1699

Data Index: 1012699 (C4 (Web Text))

Max Activating Token Index: 387

Text #15

Max Range: 5.2614. Min Range: -5.2614

Max Act: 4.9489. Min Act: -0.1700

Data Index: 741177 (C4 (Web Text))

Max Activating Token Index: 967

Text #16

Max Range: 5.2614. Min Range: -5.2614

Max Act: 4.9177. Min Act: -0.1700

Data Index: 589813 (C4 (Web Text))

Max Activating Token Index: 459

Text #17

Max Range: 5.2614. Min Range: -5.2614

Max Act: 4.9177. Min Act: -0.1700

Data Index: 517344 (C4 (Web Text))

Max Activating Token Index: 702

Text #18

Max Range: 5.2614. Min Range: -5.2614

Max Act: 4.9177. Min Act: -0.1698

Data Index: 809645 (C4 (Web Text))

Max Activating Token Index: 541

Text #19

Max Range: 5.2614. Min Range: -5.2614

Max Act: 4.8552. Min Act: -0.1700

Data Index: 88623 (C4 (Web Text))

Max Activating Token Index: 637